voxtral-tts
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill makes requests to official Mistral AI and Hugging Face API endpoints to perform speech synthesis. These are well-known and reputable services in the AI ecosystem.
- [COMMAND_EXECUTION]: The skill uses curl to interact with web APIs and media utilities like afplay and ffplay to output the generated audio. These are standard operations for a media-related tool.
- [CREDENTIALS_UNSAFE]: API keys are managed through standard environment variables ($MISTRAL_API_KEY and $HF_TOKEN), preventing the exposure of hardcoded secrets.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests Arabic text provided by the user to generate speech. Since the text is processed by a text-to-speech engine and the output is played as an audio file, it does not present a significant security risk for the execution environment.
Audit Metadata